The objective of this project is to extract the license plate information from a vehicle. The extracted information can be used with or without a database in many applications, such as electronic payment systems (toll payment, parking fee payment) and monitoring system for traffic surveillance.
In this project, proposes a way of vehicle license plate recognition. License plate recognition is divided into three parts namely license positioning, character segmentation and character recognition. In license positioning, the license positioning method is based on median filtering double edge detection. NumberPlate Detection In character segmentation, it adopts a combinative method of locating the original level and improved vertical projection segmentation algorithm. In character recognition, the recognition method is based on classification template matching of font characteristics.
The proposed license recognition method focuses on the timeliness of recognition process. Its smaller calculation largely reduces the time of license recognition, with high accuracy and precision rate at the same time. This system is implemented by Java Eclipse.